Abstract
Manually delineating brain tumor sub-locality in MR images is very time consuming, requires experienced annotators and has high inter-rater variability. Accurate unmanned segmentation of brain cancer helps in better detection and diagnosis of the disease. Further it aids in treatment planning and monitoring. With recent computational advances in graphic processing units (GPUs), drastically reducing the computational cost of neural networks, we are motivated to propose a six-layer deep autoencoder for segmenting brain tumors in MR images. The autoencoder is trained using 18\(\times \)18 2D patches extracted from multi-sequence MRI T1,T2,T1c & FLAIR. The model is pre-trained using Rmsprop and fine-tuned by exercising stochastic gradient descent (SGD). The proposed model obtained dice score of 0.88, sensitivity of 0.89 and specificity of 0.86 for the whole tumor region.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
M. Lisa, DeAngelis, Brain tumors. New England J. Med. (2001)
B.H. Menze et al., The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2015). Oct
M. Raphael, K. Venetia, H. Simon, W. Roland, M. Reyes, Parameter learning for CRF-based tissue segmentation of brain tumors, in Proceedings of MICCAI-BraTS. Munich (2015)
K. Kamnitsas et al., DeepMedic on brain tumor segmentation, in Proceedings of MICCAI-BraTs, pp. 18–22 (2016)
A. Ellawa et al., Brain tumor segmantation using random forest trained on iterative selected patients, in Proceedings of MICCAI-BraTs, pp 18–22 (2016)
A. Karnawat et al., Radiomics-based Convolutional Neural Network (RadCNN) for brain tumor segmentation on multi-parametric MRI, in Proceedings of MICCAI-BraTs, pp. 147-153 (2017)
C. Zhou et al., Brain tumor segmentation with cascaded convolutional neural networks, in Proceedings of MICCAI-BraTS Conference, pp. 328-333 (2017)
M. Islam et al., Fully convolutional network with hypercolumn features for brain tumor segmentation, in Proceedings of MICCAI-BraTs Conference, pp. 108-115 (2017)
Y. Li et al., MvNet: multi-view deep learning framework for multimodal brain tumor segmentation, in Proceedings of MICCAI-BraTS, pp. 169-174 (2017)
P.H.A. Amorim, et al., 3D U-nets for brain tumor segmentation in MICCAI 2017 BraTS challenge, in Proceedings of MICCAI-BraTS Conference, pp. 09-14 (2017)
Theano Development Team. Theano: A Python Framework for Fast Computation of Mathematical Expressions (2016). arXiv:1605.02688v1
X. Glorot et al., Understanding the difficulty of training deep feedforward neural networks, in International Conference on Artificial Intelligence and Statistics, p. 249256 (2010)
G. Hinton et al., Lecture 6.5–RmsProp: Divide the Gradient by a Running Average of its Recent Magnitude (2012)
P. Vincent et al., Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 3371-3408 (2010)
N. Srivastava, G.E. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
M. Havaei et al., Brain Tumor Segmentation with Deep Neural Networks. arXiv:1505.03540 (2016)
T. Nick, W. Max, D. Chris, B. Avants, ANTs and arboles, in PProceedings of MICCAI-BraTs. Nagoya, Japan (2013)
S. Pereira, A. Pinto, V. Alves, C.A. Silva, Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans. Med. Imaging 35(5), 1240–1251 (2016)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Naveena, C., Manjunath Aradhya, V.N., Poornachandra, S., Rudraswamy, S.B. (2021). Brain Tumor Segmentation in MRI Sequences Using Autoencoders. In: Bhateja, V., Satapathy, S.C., Travieso-González, C.M., Aradhya, V.N.M. (eds) Data Engineering and Intelligent Computing. Advances in Intelligent Systems and Computing, vol 1407. Springer, Singapore. https://doi.org/10.1007/978-981-16-0171-2_51
Download citation
DOI: https://doi.org/10.1007/978-981-16-0171-2_51
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-0170-5
Online ISBN: 978-981-16-0171-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)